© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90959
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     việc
    -0.50
     a
    -0.50
     OMITBAD
    -0.49
    TagHelpers
    -0.48
     द्वारा
    -0.48
     וגם
    -0.46
    quam
    -0.46
    所謂
    -0.45
    ánica
    -0.45
    nessed
    -0.44
    POSITIVE LOGITS
    Datuak
    0.63
    Personensuche
    0.63
    FunctionFlags
    0.63
    FieldNumber
    0.59
    bewerken
    0.57
     مشين
    0.56
     May
    0.55
    __);
    0.53
     وتسجيلات
    0.53
    parsedMessage
    0.52
    Activations Density 0.007%

    No Known Activations